Sketchy Scene Captioning: Learning Multi-level Semantic Information from Sparse Visual Scene Cues.
Lian ZhouYangdong ChenYuejie ZhangPublished in: CCL (2021)
Keyphrases
- semantic information
- visual scene
- learning algorithm
- prior knowledge
- wordnet
- higher order
- domain knowledge
- high level
- video sequences
- contextual information
- visual information
- complex scenes
- artificial intelligence
- low level features
- information extraction
- semantic knowledge
- semantic meaning
- single image
- real time
- xml documents
- image sequences
- metadata
- computer vision
- machine learning